© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 126004
    Prev
    Next
    INDEX
    Explanations

    communication, download, and organizations

    np_acts-logits-general · gemini-2.5-flash-lite

    about exploring science

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    т
    0.49
    त
    0.47
    а
    0.46
    ència
    0.43
    어서
    0.42
     Accept
    0.42
    ವಿ
    0.42
    तेरे
    0.42
    𝒕
    0.42
    ਰ
    0.42
    POSITIVE LOGITS
    ometime
    0.53
    elä
    0.47
     demok
    0.42
     wildly
    0.41
    geometric
    0.41
     HDPE
    0.41
    kent
    0.40
    eigen
    0.40
     włas
    0.40
     Jehovah
    0.39
    Activations Density 0.002%

    No Known Activations